1
|
Amorim G, Tao R, Lotspeich S, Shaw PA, Lumley T, Patel RC, Shepherd BE. Three-phase generalized raking and multiple imputation estimators to address error-prone data. Stat Med 2024; 43:379-394. [PMID: 37987515 PMCID: PMC10842111 DOI: 10.1002/sim.9967] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2023] [Revised: 09/23/2023] [Accepted: 11/09/2023] [Indexed: 11/22/2023]
Abstract
Validation studies are often used to obtain more reliable information in settings with error-prone data. Validated data on a subsample of subjects can be used together with error-prone data on all subjects to improve estimation. In practice, more than one round of data validation may be required, and direct application of standard approaches for combining validation data into analyses may lead to inefficient estimators since the information available from intermediate validation steps is only partially considered or even completely ignored. In this paper, we present two novel extensions of multiple imputation and generalized raking estimators that make full use of all available data. We show through simulations that incorporating information from intermediate steps can lead to substantial gains in efficiency. This work is motivated by and illustrated in a study of contraceptive effectiveness among 83 671 women living with HIV, whose data were originally extracted from electronic medical records, of whom 4732 had their charts reviewed, and a subsequent 1210 also had a telephone interview to validate key study variables.
Collapse
Affiliation(s)
- Gustavo Amorim
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Ran Tao
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt Genetics Institute, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Sarah Lotspeich
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Statistical Sciences, Wake Forest University, Winston-Salem, NC, USA
| | - Pamela A. Shaw
- Kaiser Permanente Washington Health Research Institute, Seattle, WA, USA
| | - Thomas Lumley
- Department of Statistics, University of Auckland, Auckland, New Zealand
| | - Rena C. Patel
- Department of Medicine, University of Washington, Seattle, WA, USA
| | - Bryan E. Shepherd
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA
| |
Collapse
|
2
|
Shih JH, Albert PS, Fine J, Liu D. An imputation approach for a time-to-event analysis subject to missing outcomes due to noncoverage in disease registries. Biostatistics 2023; 25:117-133. [PMID: 36534828 PMCID: PMC10939403 DOI: 10.1093/biostatistics/kxac049] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2022] [Revised: 11/29/2022] [Accepted: 12/04/2022] [Indexed: 12/17/2023] Open
Abstract
Disease incidence data in a national-based cohort study would ideally be obtained through a national disease registry. Unfortunately, no such registry currently exists in the United States. Instead, the results from individual state registries need to be combined to ascertain certain disease diagnoses in the United States. The National Cancer Institute has initiated a program to assemble all state registries to provide a complete assessment of all cancers in the United States. Unfortunately, not all registries have agreed to participate. In this article, we develop an imputation-based approach that uses self-reported cancer diagnosis from longitudinally collected questionnaires to impute cancer incidence not covered by the combined registry. We propose a two-step procedure, where in the first step a mover-stayer model is used to impute a participant's registry coverage status when it is only reported at the time of the questionnaires given at 10-year intervals and the time of the last-alive vital status and death. In the second step, we propose a semiparametric working model, fit using an imputed coverage area sample identified from the mover-stayer model, to impute registry-based survival outcomes for participants in areas not covered by the registry. The simulation studies show the approach performs well as compared with alternative ad hoc approaches for dealing with this problem. We illustrate the methodology with an analysis that links the United States Radiologic Technologists study cohort with the combined registry that includes 32 of the 50 states.
Collapse
Affiliation(s)
- Joanna H Shih
- Biometric Research Program, Division of Cancer Treatment and Diagnosis, National Cancer Institute, 9609 Medical Center Drive, Bethesda, MD 20892, USA
| | - Paul S Albert
- Biostatistics Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, 9609 Medical Center Drive, Bethesda, MD 20892, USA
| | - Jason Fine
- Biostatistics Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, 9609 Medical Center Drive, Bethesda, MD 20892, USA
| | - Danping Liu
- Biostatistics Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, 9609 Medical Center Drive, Bethesda, MD 20892, USA
| |
Collapse
|
3
|
Shepherd BE, Han K, Chen T, Bian A, Pugh S, Duda SN, Lumley T, Heerman WJ, Shaw PA. Multiwave validation sampling for error-prone electronic health records. Biometrics 2023; 79:2649-2663. [PMID: 35775996 PMCID: PMC10525037 DOI: 10.1111/biom.13713] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2022] [Accepted: 06/16/2022] [Indexed: 11/29/2022]
Abstract
Electronic health record (EHR) data are increasingly used for biomedical research, but these data have recognized data quality challenges. Data validation is necessary to use EHR data with confidence, but limited resources typically make complete data validation impossible. Using EHR data, we illustrate prospective, multiwave, two-phase validation sampling to estimate the association between maternal weight gain during pregnancy and the risks of her child developing obesity or asthma. The optimal validation sampling design depends on the unknown efficient influence functions of regression coefficients of interest. In the first wave of our multiwave validation design, we estimate the influence function using the unvalidated (phase 1) data to determine our validation sample; then in subsequent waves, we re-estimate the influence function using validated (phase 2) data and update our sampling. For efficiency, estimation combines obesity and asthma sampling frames while calibrating sampling weights using generalized raking. We validated 996 of 10,335 mother-child EHR dyads in six sampling waves. Estimated associations between childhood obesity/asthma and maternal weight gain, as well as other covariates, are compared to naïve estimates that only use unvalidated data. In some cases, estimates markedly differ, underscoring the importance of efficient validation sampling to obtain accurate estimates incorporating validated data.
Collapse
Affiliation(s)
- Bryan E. Shepherd
- Department of Biostatistics, Vanderbilt University, Nashville, Tennessee, USA
| | - Kyunghee Han
- Depart. of Mathematics, Statistics, and Computer Science; Univ. of Illinois at Chicago
| | - Tong Chen
- Department of Statistics, University of Auckland
| | - Aihua Bian
- Department of Biostatistics, Vanderbilt University, Nashville, Tennessee, USA
| | - Shannon Pugh
- Department of Emergency Medicine, Vanderbilt University Medical Center
| | - Stephany N. Duda
- Department of Biomedical Informatics, Vanderbilt University Medical Center
| | | | | | - Pamela A. Shaw
- Biostatistics Unit, Kaiser Permanente Washington Health Research Institute
| |
Collapse
|
4
|
Hong C, Liang L, Yuan Q, Cho K, Liao KP, Pencina MJ, Christiani DC, Cai T. Semi-supervised calibration of noisy event risk (SCANER) with electronic health records. J Biomed Inform 2023; 144:104425. [PMID: 37331495 PMCID: PMC10478159 DOI: 10.1016/j.jbi.2023.104425] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2022] [Revised: 05/05/2023] [Accepted: 05/19/2023] [Indexed: 06/20/2023]
Abstract
OBJECTIVE Electronic health records (EHR), containing detailed longitudinal clinical information on a large number of patients and covering broad patient populations, open opportunities for comprehensive predictive modeling of disease progression and treatment response. However, since EHRs were originally constructed for administrative purposes not for research, in the EHR-linked studies, it is often not feasible to capture reliable information for analytical variables, especially in the survival setting, when both accurate event status and event times are needed for model building. For example, progression-free survival (PFS), a commonly used survival outcome for cancer patients, often involves complex information embedded in free-text clinical notes and cannot be extracted reliably. Proxies of PFS time such as time to the first mention of progression in the notes are at best good approximations to the true event time. This leads to difficulty in efficiently estimating event rates for an EHR patient cohort. Estimating survival rates based on error-prone outcome definitions can lead to biased results and hamper the power in the downstream analysis. On the other hand, extracting accurate event time information via manual annotation is time and resource intensive. The objective of this study is to develop a calibrated survival rate estimator using noisy outcomes from EHR data. MATERIALS AND METHODS In this paper, we propose a two-stage semi-supervised calibration of noisy event rate (SCANER) estimator that can effectively overcome censoring induced dependency and attains more robust performance (i.e., not sensitive to misspecification of the imputation model) by fully utilizing both a small-labeled set of gold-standard survival outcomes annotated via manual chart review and a set of proxy features automatically captured via EHR in the unlabeled set. We validate the SCANER estimator by estimating the PFS rates for a virtual cohort of lung cancer patients from one large tertiary care center and the ICU-free survival rates for COVID patients from two large tertiary care centers. RESULTS In terms of survival rate estimates, the SCANER had very similar point estimates compared to the complete-case Kaplan Meier estimator. On the other hand, other benchmark methods for comparison, which fail to account for the induced dependency between event time and the censoring time conditioning on surrogate outcomes, produced biased results across all three case studies. In terms of standard errors, the SCANER estimator was more efficient than the KM estimator, with up to 50% efficiency gain. CONCLUSION The SCANER estimator achieves more efficient, robust, and accurate survival rate estimates compared to existing approaches. This promising new approach can also improve the resolution (i.e., granularity of event time) by using labels conditioning on multiple surrogates, particularly among less common or poorly coded conditions.
Collapse
Affiliation(s)
- Chuan Hong
- Duke University, Durham, NC, USA; Harvard Medical School, Boston, MA, USA
| | - Liang Liang
- Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Qianyu Yuan
- Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Kelly Cho
- Harvard Medical School, Boston, MA, USA; VA Boston Healthcare System, Boston, MA, USA; Brigham and Women's Hospital, Boston, MA, USA
| | - Katherine P Liao
- Harvard Medical School, Boston, MA, USA; VA Boston Healthcare System, Boston, MA, USA; Brigham and Women's Hospital, Boston, MA, USA
| | | | - David C Christiani
- Harvard T.H. Chan School of Public Health, Boston, MA, USA; Massachusetts General Hospital, Boston, MA, USA
| | - Tianxi Cai
- Harvard T.H. Chan School of Public Health, Boston, MA, USA; Massachusetts General Hospital, Boston, MA, USA.
| |
Collapse
|
5
|
Lotspeich SC, Amorim GGC, Shaw PA, Tao R, Shepherd BE. Optimal multiwave validation of secondary use data with outcome and exposure misclassification. CAN J STAT 2023. [DOI: 10.1002/cjs.11772] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/03/2023]
|
6
|
Lotspeich SC, Shepherd BE, Amorim GGC, Shaw PA, Tao R. Efficient odds ratio estimation under two-phase sampling using error-prone data from a multi-national HIV research cohort. Biometrics 2022; 78:1674-1685. [PMID: 34213008 PMCID: PMC8720323 DOI: 10.1111/biom.13512] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2020] [Revised: 05/19/2021] [Accepted: 06/17/2021] [Indexed: 12/30/2022]
Abstract
Persons living with HIV engage in routine clinical care, generating large amounts of data in observational HIV cohorts. These data are often error-prone, and directly using them in biomedical research could bias estimation and give misleading results. A cost-effective solution is the two-phase design, under which the error-prone variables are observed for all patients during Phase I, and that information is used to select patients for data auditing during Phase II. For example, the Caribbean, Central, and South America network for HIV epidemiology (CCASAnet) selected a random sample from each site for data auditing. Herein, we consider efficient odds ratio estimation with partially audited, error-prone data. We propose a semiparametric approach that uses all information from both phases and accommodates a number of error mechanisms. We allow both the outcome and covariates to be error-prone and these errors to be correlated, and selection of the Phase II sample can depend on Phase I data in an arbitrary manner. We devise a computationally efficient, numerically stable EM algorithm to obtain estimators that are consistent, asymptotically normal, and asymptotically efficient. We demonstrate the advantages of the proposed methods over existing ones through extensive simulations. Finally, we provide applications to the CCASAnet cohort.
Collapse
Affiliation(s)
- Sarah C. Lotspeich
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, U.S.A
| | - Bryan E. Shepherd
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, U.S.A
| | - Gustavo G. C. Amorim
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, U.S.A
| | - Pamela A. Shaw
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, U.S.A
| | - Ran Tao
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, U.S.A
- Vanderbilt Genetics Institute, Vanderbilt University Medical Center, Nashville, TN, U.S.A
| |
Collapse
|
7
|
Chen T, Lumley T. Optimal sampling for design-based estimators of regression models. Stat Med 2022; 41:1482-1497. [PMID: 34989429 PMCID: PMC8918008 DOI: 10.1002/sim.9300] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2021] [Revised: 12/02/2021] [Accepted: 12/10/2021] [Indexed: 11/05/2022]
Abstract
Two-phase designs measure variables of interest on a subcohort where the outcome and covariates are readily available or cheap to collect on all individuals in the cohort. Given limited resource availability, it is of interest to find an optimal design that includes more informative individuals in the final sample. We explore the optimal designs and efficiencies for analyses by design-based estimators. Generalized raking is an efficient class of design-based estimators, and they improve on the inverse-probability weighted (IPW) estimator by adjusting weights based on the auxiliary information. We derive a closed-form solution of the optimal design for estimating regression coefficients from generalized raking estimators. We compare it with the optimal design for analysis via the IPW estimator and other two-phase designs in measurement-error settings. We consider general two-phase designs where the outcome variable and variables of interest can be continuous or discrete. Our results show that the optimal designs for analyses by the two classes of design-based estimators can be very different. The optimal design for analysis via the IPW estimator is optimal for IPW estimation and typically gives near-optimal efficiency for generalized raking estimation, though we show there is potential improvement in some settings.
Collapse
Affiliation(s)
- Tong Chen
- Department of Statistics, University of Auckland, Auckland, New Zealand
| | - Thomas Lumley
- Department of Statistics, University of Auckland, Auckland, New Zealand
| |
Collapse
|
8
|
Manderson AA, Goudie RJB. Combining chains of Bayesian models with Markov melding. BAYESIAN ANALYSIS 2022; 18:807-840. [PMID: 37587923 PMCID: PMC7614958 DOI: 10.1214/22-ba1327] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 08/18/2023]
Abstract
A challenge for practitioners of Bayesian inference is specifying a model that incorporates multiple relevant, heterogeneous data sets. It may be easier to instead specify distinct submodels for each source of data, then join the submodels together. We consider chains of submodels, where submodels directly relate to their neighbours via common quantities which may be parameters or deterministic functions thereof. We propose chained Markov melding, an extension of Markov melding, a generic method to combine chains of submodels into a joint model. One challenge we address is appropriately capturing the prior dependence between common quantities within a submodel, whilst also reconciling differences in priors for the same common quantity between two adjacent submodels. Estimating the posterior of the resulting overall joint model is also challenging, so we describe a sampler that uses the chain structure to incorporate information contained in the submodels in multiple stages, possibly in parallel. We demonstrate our methodology using two examples. The first example considers an ecological integrated population model, where multiple data sets are required to accurately estimate population immigration and reproduction rates. We also consider a joint longitudinal and time-to-event model with uncertain, submodel-derived event times. Chained Markov melding is a conceptually appealing approach to integrating submodels in these settings.
Collapse
Affiliation(s)
- Andrew A. Manderson
- MRC Biostatistics Unit, University of Cambridge, United Kingdom, and The Alan Turing Institute
| | | |
Collapse
|
9
|
Patel RC, Amorim G, Jakait B, Shepherd BE, Mocello AR, Musick B, Bernard C, Onono M, Bukusi EA, Wools-Kaloustian K, Cohen CR, Yiannoutsos CT. Pregnancies among women living with HIV using contraceptives and antiretroviral therapy in western Kenya: a retrospective, cohort study. BMC Med 2021; 19:178. [PMID: 34384443 PMCID: PMC8361857 DOI: 10.1186/s12916-021-02043-z] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/24/2021] [Accepted: 06/21/2021] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Preventing unintended pregnancies is paramount for women living with HIV (WLHIV). Previous studies have suggested that efavirenz-containing antiretroviral therapy (ART) reduces contraceptive effectiveness of implants, but there are uncertainties regarding the quality of the electronic medical record (EMR) data used in these prior studies. METHODS We conducted a retrospective, cohort study of EMR data from 2011 to 2015 among WLHIV of reproductive age accessing HIV care in public facilities in western Kenya. We validated a large subsample of records with manual chart review and telephone interviews. We estimated adjusted incidence rate ratios (aIRRs) with Poisson regression accounting for the validation sampling using inverse probability weighting and generalized raking. RESULTS A total of 85,324 women contributed a total of 170,845 women-years (w-y) of observation time; a subset of 5080 women had their charts reviewed, and 1285 underwent interviews. Among implant users, the aIRR of pregnancy for efavirenz- vs. nevirapine-containing ART was 1.9 (95% CI 1.6, 2.4) using EMR data only and 3.2 (95% CI 1.8, 5.7) when additionally using both chart review and interview validated data. Among efavirenz users, the aIRR of pregnancy for depomedroxyprogesterone acetate (DMPA) vs. implant use was 1.8 (95% CI 1.5, 2.1) in EMR only and 2.4 (95% CI 1.0, 6.1) using validated data. CONCLUSION Pregnancy rates are higher when contraceptive implants are concomitantly used with efavirenz-containing ART, though rates were similar to leading alternative contraceptive methods such as DMPA. Our data provides policymakers, program staff, and WLHIV greater confidence in guiding their decision-making around contraceptive and ART options. Our novel, 3-phase validation sampling provides an innovative tool for using routine EMR data to improve the robustness of data quality.
Collapse
Affiliation(s)
- Rena C Patel
- Division of Allergy and Infectious Diseases, Department of Medicine and Department of Global Health, University of Washington, UW Box 359927, 325 Ninth Avenue, Seattle, WA, 98104, USA.
| | - Gustavo Amorim
- Department of Biostatistics, Vanderbilt University, Nashville, TN, USA
| | - Beatrice Jakait
- Moi Teaching & Referral Hospital/Moi University & Academic Model Providing Access to Healthcare (AMPATH), Eldoret, Kenya
| | - Bryan E Shepherd
- Department of Biostatistics, Vanderbilt University, Nashville, TN, USA
| | - A Rain Mocello
- Bixby Center for Global Reproductive Health and Department of Obstetrics, Gynecology & Reproductive Health, University of California, San Francisco, San Francisco, CA, USA
| | - Beverly Musick
- Department of Biostatistics, School of Medicine, Indiana University, Indianapolis, IN, USA
| | - Caitlin Bernard
- Division of Family Planning, Department of Obstetrics & Gynecology, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Maricianah Onono
- Centre for Microbiology Research, Kenya Medical Research Institute, Nairobi, Kenya
| | - Elizabeth A Bukusi
- Centre for Microbiology Research, Kenya Medical Research Institute, Nairobi, Kenya
| | | | - Craig R Cohen
- Bixby Center for Global Reproductive Health and Department of Obstetrics, Gynecology & Reproductive Health, University of California, San Francisco, San Francisco, CA, USA
| | - Constantin T Yiannoutsos
- Department of Biostatistics, R.M. Fairbanks School of Public Health, Indiana University, Indianapolis, IN, USA
| |
Collapse
|
10
|
Oh EJ, Shepherd BE, Lumley T, Shaw PA. Improved generalized raking estimators to address dependent covariate and failure-time outcome error. Biom J 2021; 63:1006-1027. [PMID: 33709462 PMCID: PMC8211389 DOI: 10.1002/bimj.202000187] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2020] [Revised: 10/05/2020] [Accepted: 01/05/2021] [Indexed: 11/12/2022]
Abstract
Biomedical studies that use electronic health records (EHR) data for inference are often subject to bias due to measurement error. The measurement error present in EHR data is typically complex, consisting of errors of unknown functional form in covariates and the outcome, which can be dependent. To address the bias resulting from such errors, generalized raking has recently been proposed as a robust method that yields consistent estimates without the need to model the error structure. We provide rationale for why these previously proposed raking estimators can be expected to be inefficient in failure-time outcome settings involving misclassification of the event indicator. We propose raking estimators that utilize multiple imputation, to impute either the target variables or auxiliary variables, to improve the efficiency. We also consider outcome-dependent sampling designs and investigate their impact on the efficiency of the raking estimators, either with or without multiple imputation. We present an extensive numerical study to examine the performance of the proposed estimators across various measurement error settings. We then apply the proposed methods to our motivating setting, in which we seek to analyze HIV outcomes in an observational cohort with EHR data from the Vanderbilt Comprehensive Care Clinic.
Collapse
Affiliation(s)
- Eric J. Oh
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA, USA
| | - Bryan E. Shepherd
- Department of Biostatistics, Vanderbilt University, Nashville, TN, USA
| | - Thomas Lumley
- Department of Statistics, University of Auckland, Auckland, New Zealand
| | - Pamela A. Shaw
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA, USA
| |
Collapse
|
11
|
Giganti MJ, Shepherd BE. Multiple-Imputation Variance Estimation in Studies With Missing or Misclassified Inclusion Criteria. Am J Epidemiol 2020; 189:1628-1632. [PMID: 32685964 PMCID: PMC7705600 DOI: 10.1093/aje/kwaa153] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2019] [Revised: 07/13/2020] [Accepted: 07/14/2020] [Indexed: 11/15/2022] Open
Abstract
In observational studies using routinely collected data, a variable with a high level of missingness or misclassification may determine whether an observation is included in the analysis. In settings where inclusion criteria are assessed after imputation, the popular multiple-imputation variance estimator proposed by Rubin ("Rubin's rules" (RR)) is biased due to incompatibility between imputation and analysis models. While alternative approaches exist, most analysts are not familiar with them. Using partially validated data from a human immunodeficiency virus cohort, we illustrate the calculation of an imputation variance estimator proposed by Robins and Wang (RW) in a scenario where the study exclusion criteria are based on a variable that must be imputed. In this motivating example, the corresponding imputation variance estimate for the log odds was 29% smaller using the RW estimator than using the RR estimator. We further compared these 2 variance estimators with a simulation study which showed that coverage probabilities of 95% confidence intervals based on the RR estimator were too high and became worse as more observations were imputed and more subjects were excluded from the analysis. The RW imputation variance estimator performed much better and should be employed when there is incompatibility between imputation and analysis models. We provide analysis code to aid future analysts in implementing this method.
Collapse
Affiliation(s)
- Mark J Giganti
- Correspondence to Dr. Mark J. Giganti, Center for Biostatistics in AIDS Research, Harvard T.H. Chan School of Public Health, 651 Huntington Avenue, Boston, MA 02115 (e-mail: )
| | | |
Collapse
|
12
|
Shepherd BE, Shaw PA. Errors in multiple variables in human immunodeficiency virus (HIV) cohort and electronic health record data: statistical challenges and opportunities. STATISTICAL COMMUNICATIONS IN INFECTIOUS DISEASES 2020; 12:20190015. [PMID: 35880997 PMCID: PMC9204761 DOI: 10.1515/scid-2019-0015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/15/2019] [Accepted: 08/21/2020] [Indexed: 06/15/2023]
Abstract
Objectives: Observational data derived from patient electronic health records (EHR) data are increasingly used for human immunodeficiency virus/acquired immunodeficiency syndrome (HIV/AIDS) research. There are challenges to using these data, in particular with regards to data quality; some are recognized, some unrecognized, and some recognized but ignored. There are great opportunities for the statistical community to improve inference by incorporating validation subsampling into analyses of EHR data.Methods: Methods to address measurement error, misclassification, and missing data are relevant, as are sampling designs such as two-phase sampling. However, many of the existing statistical methods for measurement error, for example, only address relatively simple settings, whereas the errors seen in these datasets span multiple variables (both predictors and outcomes), are correlated, and even affect who is included in the study.Results/Conclusion: We will discuss some preliminary methods in this area with a particular focus on time-to-event outcomes and outline areas of future research.
Collapse
Affiliation(s)
- Bryan E. Shepherd
- Biostatistics, Vanderbilt University, 2525 West End, Suite 11000, 37203Nashville, Tennessee, USA
| | - Pamela A. Shaw
- Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA
| |
Collapse
|